rewire.it
Configuration

SpliceAI 1.3.1

This MFASS evaluation uses the official SpliceAI 1.3.1 five-model ensemble in genomic context.

SourcesMFASS v2 run_spliceai.py · run_spliceai.py module documentation and recorded runner configuration

1 evaluation · 3 metric rows

How it worksEvaluated pipeline
Evaluated pipeline1. Variant in GRCh38. Then: 2. SpliceAI ensemble. Then: 3. Acceptor / donor delta scores. Then: 4. Maximum delta. Then: 5. Variant rankingEvaluated pipeline1. Variant in GRCh38. Then: 2. SpliceAI ensemble. Then: 3. Acceptor / donor delta scores. Then: 4. Maximum delta. Then: 5. Variant rankingEvaluated pipeline1. Variant in GRCh38. Then: 2. SpliceAI ensemble. Then: 3. Acceptor / donor delta scores. Then: 4. Maximum delta. Then: 5. Variant ranking

Schematic of the pinned MFASS configuration; this does not generalise to every member of the model family.

SourcesMFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e

Underlying model: SpliceAI. Results on this page belong to this configuration and its evaluated settings.

At a glance

Model type

Pretrained splice-site specialist ensemble

SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure

Biological inputs

Variant genomic coordinates and GRCh38 reference/annotation

SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure

Outputs

Maximum splice acceptor/donor gain/loss delta score

SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 3 metric rows. Different protocols are not a single leaderboard.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
SpliceAI 1.3.1 on MFASS v2

Unchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset.

Rewire evaluation · Evaluation metadata: reproduced

0.8055241740253153 auroc

Unit: fraction · Direction: higher

Uncertainty: Point estimate; see paired-comparison artifacts.

Coverage (scored/eligible): 8194/8324

reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: auroc

Source checking is not independent reproduction.

0.2986855472760137 average_precision

Unit: fraction · Direction: higher

Uncertainty: Point estimate; see paired-comparison artifacts.

Coverage (scored/eligible): 8194/8324

reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: average_precision

Source checking is not independent reproduction.

0.64 precision_at_100

Unit: fraction · Direction: higher

Uncertainty: Point estimate; see paired-comparison artifacts.

Coverage (scored/eligible): 8194/8324

reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: precision_at_100

Source checking is not independent reproduction.

How it works

Evaluated procedure

The runner scores variants against GRCh38 with bundled annotations and unmasked outputs. It ranks variants by the largest acceptor/donor gain or loss delta score. Its specialist predictions were retained unchanged for the corrected v2 comparison.

SourcesMFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e

Strengths and limitations

Strengths and considerations

  • Uses a pretrained splice specialist without fitting to MFASS labels.
    SourcesMFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e

Limitations and conditions

  • The genomic context differs from the assay construct. Missing predictions and possible exon overlap with specialist training data must be considered.
    SourcesMFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e
Profile review details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Stable record: rewire-model-spliceai-1-3-1

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Inputs, outputs and configuration
PropertyDescription and evidence
Model typePretrained splice-site specialist ensemble
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
Architecture / procedureOfficial five-model SpliceAI ensemble; score is max(DS_AG, DS_AL, DS_DG, DS_DL), with masking disabled.
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
Biological inputsVariant genomic coordinates and GRCh38 reference/annotation
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
OutputsMaximum splice acceptor/donor gain/loss delta score
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
ParametersAn aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources
SourcesMFASS v2 run_spliceai.py · Pinned runner configuration and implementation; inspected for aggregate parameter count (component sizes are not added without an exact configuration)
Training data / fittingNo MFASS-label fitting by the runner. Upstream transcript overlap with assayed exons remains unchecked.
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
Context limits10,000-bp genomic context; distance_D=50; mask_M=0.
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
Known versions / configurationSpliceAI 1.3.1; bundled spliceai1–5.h5 weights
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
AccessPublic pinned benchmark runner with external genome and SpliceAI dependencies.
SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure
Code licenceMIT for the Rewire runner at the reviewed revision. Upstream SpliceAI: PolyForm Strict 1.0.0. These are separate component licences.
Sources (2)Rewire benchmark runner licence; github.com/Illumina/SpliceAI LICENSE · LICENSE; complete MIT grant; upstream LICENSE
Weights licenceSpliceAI trained models are CC BY-NC 4.0 for academic/non-commercial use; commercial use requires separate Illumina terms.
Sourcesgithub.com/Illumina/SpliceAI README.md · README.md; License

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statementOriginal source and locationReview and provenance
Diagram caption

Schematic of the pinned MFASS configuration; this does not generalise to every member of the model family.

Individual claims
MFASS v2 pinned rewire artifacts

Original source ↗

benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T10:50:02Z

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d

Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash

Diagram steps

["Variant in GRCh38","SpliceAI ensemble","Acceptor / donor delta scores","Maximum delta","Variant ranking"]

Individual claims
MFASS v2 pinned rewire artifacts

Original source ↗

benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T10:50:02Z

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d

Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash

Diagram title

Evaluated pipeline

Individual claims
MFASS v2 pinned rewire artifacts

Original source ↗

benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T10:50:02Z

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.diagram.title

Source artifact SHA-256: a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d

Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash

Model type

Pretrained splice-site specialist ensemble

Individual claims
MFASS v2 run_spliceai.py

Original source ↗

run_spliceai.py; module documentation, main() configuration and scoring procedure

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T20:47:15.959417+00:00

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: 3709bc12997744b77ce2f9ea4de79cdcafa6ffc136b61bb020f57e43acbe8685

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Architecture / procedure

Official five-model SpliceAI ensemble; score is max(DS_AG, DS_AL, DS_DG, DS_DL), with masking disabled.

Individual claims
MFASS v2 run_spliceai.py

Original source ↗

run_spliceai.py; module documentation, main() configuration and scoring procedure

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T20:47:15.959417+00:00

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: 3709bc12997744b77ce2f9ea4de79cdcafa6ffc136b61bb020f57e43acbe8685

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Weights licence

SpliceAI trained models are CC BY-NC 4.0 for academic/non-commercial use; commercial use requires separate Illumina terms.

Individual claims
github.com/Illumina/SpliceAI README.md

Original source ↗

README.md; License

Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079
Retrieved: 2026-09-16T19:46:17.769160+00:00

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.10.value

Source artifact SHA-256: 8e5203afe343100832391e6155c7112f15cfe60bf0c21681d64e3420f854ef4d

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Biological inputs

Variant genomic coordinates and GRCh38 reference/annotation

Individual claims
MFASS v2 run_spliceai.py

Original source ↗

run_spliceai.py; module documentation, main() configuration and scoring procedure

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T20:47:15.959417+00:00

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: 3709bc12997744b77ce2f9ea4de79cdcafa6ffc136b61bb020f57e43acbe8685

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Outputs

Maximum splice acceptor/donor gain/loss delta score

Individual claims
MFASS v2 run_spliceai.py

Original source ↗

run_spliceai.py; module documentation, main() configuration and scoring procedure

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T20:47:15.959417+00:00

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: 3709bc12997744b77ce2f9ea4de79cdcafa6ffc136b61bb020f57e43acbe8685

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Parameters

An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources.

Individual claims
MFASS v2 run_spliceai.py

Original source ↗

Pinned runner configuration and implementation; inspected for aggregate parameter count (component sizes are not added without an exact configuration)

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T20:47:15.959417+00:00

unreported

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: 3709bc12997744b77ce2f9ea4de79cdcafa6ffc136b61bb020f57e43acbe8685

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Training data / fitting

No MFASS-label fitting by the runner. Upstream transcript overlap with assayed exons remains unchecked.

Individual claims
MFASS v2 run_spliceai.py

Original source ↗

run_spliceai.py; module documentation, main() configuration and scoring procedure

Version: bee9133b83f3aedaf2bbb9013f1875515845607e
Retrieved: 2026-09-16T20:47:15.959417+00:00

source checked

automated source review · 2026-09-16

Audit details

Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: 3709bc12997744b77ce2f9ea4de79cdcafa6ffc136b61bb020f57e43acbe8685

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: source checked

5 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: rewire-model-spliceai-1-3-1

areas
dna-genomes
entity level
method
version
bee9133b83f3aedaf2bbb9013f1875515845607e
reported name
SpliceAI 1.3.1
historical missing metadata
metadata review scope
historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds
model
entity classification
review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: evidence-reported-rewire-run-spliceai; source locator: run_spliceai.py; module documentation, main() configuration and scoring procedure | run_spliceai.py module documentation and recorded runner configuration; ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.
Related records

Suggest a correction